matlab-deep-learning/Quantized-Deep-Neural-Network-on-Jetson-AGX-Xavier

How to create, train and quantize network, then integrate it into pre/post image processing and generate CUDA C++ code for targeting Jetson AGX Xavier

34
/ 100
Emerging

This project helps manufacturing engineers and quality control specialists create efficient, on-device systems for detecting defects in images. It takes raw image data and a trained deep learning model, then outputs a highly optimized, smaller model and C++ code for deployment. This is ideal for those who need to run complex image analysis directly on embedded hardware like NVIDIA Jetson devices.

No commits in the last 6 months.

Use this if you need to deploy deep learning models for image-based defect detection onto resource-constrained edge devices, while maintaining high performance.

Not ideal if your application does not involve embedded systems, defect detection, or you prefer not to use MATLAB and GPU Coder for development.

defect-detection quality-control embedded-vision manufacturing-automation edge-ai
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

12

Forks

2

Language

MATLAB

License

Last pushed

May 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/matlab-deep-learning/Quantized-Deep-Neural-Network-on-Jetson-AGX-Xavier"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.